[GH-ISSUE #14399] Nerdsking Coder Family of Models #35113

Closed
opened 2026-04-22 19:21:11 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @rastamancoder on GitHub (Feb 24, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14399

Why I can't find Nerdsking Python coders? (Nerdsking/nerdsking-python-coder-3B-i and the Nerdsking/Nerdsking-python-coder-7B-i).

They are extremelly fast (answer the 160 questions in HumanEval in 3,5 minutes, while Nambeige takes 6 hours using the same hardware...) and achieves 88% in HumanEval.

I benchmarked the 3B version myself, and while it has no thinking mode, it really reaches that mark. It's perfect for code completion and simple function program building.

Please consider adding those.

https://huggingface.co/Nerdsking/nerdsking-python-coder-3B-i
https://huggingface.co/Nerdsking/Nerdsking-python-coder-7B-i

Thx a lot.

Originally created by @rastamancoder on GitHub (Feb 24, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14399 Why I can't find Nerdsking Python coders? (Nerdsking/nerdsking-python-coder-3B-i and the Nerdsking/Nerdsking-python-coder-7B-i). They are extremelly fast (answer the 160 questions in HumanEval in 3,5 minutes, while Nambeige takes 6 hours using the same hardware...) and achieves 88% in HumanEval. I benchmarked the 3B version myself, and while it has no thinking mode, it really reaches that mark. It's perfect for code completion and simple function program building. Please consider adding those. https://huggingface.co/Nerdsking/nerdsking-python-coder-3B-i https://huggingface.co/Nerdsking/Nerdsking-python-coder-7B-i Thx a lot.
GiteaMirror added the feature request label 2026-04-22 19:21:11 -05:00
Author
Owner

@rick-github commented on GitHub (Feb 24, 2026):

qwen2 architecture so should be simple to import.

<!-- gh-comment-id:3955216871 --> @rick-github commented on GitHub (Feb 24, 2026): `qwen2` architecture so should be simple to [import](https://github.com/ollama/ollama/blob/main/docs/import.mdx#Importing-a-GGUF-based-model-or-adapter).
Author
Owner

@rick-github commented on GitHub (Feb 24, 2026):

$ ollama run hf.co/Nerdsking/nerdsking-python-coder-3B-i:Q5_K_M
pulling manifest 
pulling 469fb39a1c93: 100% ▕██████████████████▏ 2.2 GB                         
pulling e94a8ecb9327: 100% ▕██████████████████▏ 1.6 KB                         
pulling 94ecee160ddf: 100% ▕██████████████████▏  478 B                         
verifying sha256 digest 
writing manifest 
success 
>>> hello
Hello! How can I assist you today?

>>> Send a message (/? for help)
<!-- gh-comment-id:3955221787 --> @rick-github commented on GitHub (Feb 24, 2026): ```console $ ollama run hf.co/Nerdsking/nerdsking-python-coder-3B-i:Q5_K_M pulling manifest pulling 469fb39a1c93: 100% ▕██████████████████▏ 2.2 GB pulling e94a8ecb9327: 100% ▕██████████████████▏ 1.6 KB pulling 94ecee160ddf: 100% ▕██████████████████▏ 478 B verifying sha256 digest writing manifest success >>> hello Hello! How can I assist you today? >>> Send a message (/? for help) ```
Author
Owner

@rastamancoder commented on GitHub (Feb 24, 2026):

It would be nice to have it automatically since those 2 are the best small instruct models for python presently and are ultra fast.

<!-- gh-comment-id:3955291124 --> @rastamancoder commented on GitHub (Feb 24, 2026): It would be nice to have it automatically since those 2 are the best small instruct models for python presently and are ultra fast.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#35113